如何根据R中其他文件的名称获取文件名？_R_File_Tidyverse_Filenames_Magrittr

如何根据R中其他文件的名称获取文件名？

r file

如何根据R中其他文件的名称获取文件名？,r,file,tidyverse,filenames,magrittr,R,File,Tidyverse,Filenames,Magrittr,我有一个包含如下文件的文件目录数据： data |___ UPA.csv |___ M_B.csv |___ M_C.csv |___ M_D.csv |___ M_E.csv Genes AC018653.3 AC022509.1 AC022509.2 AC055720.2 AC082651.1 AC084346.2 AC084824.4 AC092171.4 AC092803.2 AC084346.2 AD097808.3 AC084824.4 ADFR3564.8

我有一个包含如下文件的文件目录数据：

data
  |___ UPA.csv
  |___ M_B.csv
  |___ M_C.csv
  |___ M_D.csv
  |___ M_E.csv

Genes
AC018653.3
AC022509.1
AC022509.2
AC055720.2
AC082651.1
AC084346.2
AC084824.4
AC092171.4
AC092803.2

AC084346.2
AD097808.3
AC084824.4
ADFR3564.8
A1982983.4

AC098789.3
AC022509.2
AC783546.3
AC055720.2

AC018653.3
AS989473.9
AC022509.1
AE378467.1

M_B.csv: AC084346.2, AC084824.4
M_C.csv: AC022509.2, AC055720.2
M_D.csv: AC018653.3, AC022509.1

setwd("/data/")
library(tidyverse)
library(magrittr)

genes <- Sys.glob(file.path("M_*.csv"))
genes.read <- lapply(genes,function(x) read.delim(x, header = FALSE))
genes.read <- lapply(genes.read, function(x) set_colnames(x, "Genes"))
ref2 <- list.files(pattern = "UP")
ref2
ref.read <- read.delim(ref2[[1]])
intersect <- lapply(seq_along(genes.read), function(x) 
  intersect(genes.read[[x]], ref.read))
for(i in 1:length(genes.read)) { 
  cat(genes[[i]],":",intersect[[i]]$Genes, "\n")
}

UPA.csv

如下所示：

data
  |___ UPA.csv
  |___ M_B.csv
  |___ M_C.csv
  |___ M_D.csv
  |___ M_E.csv

Genes
AC018653.3
AC022509.1
AC022509.2
AC055720.2
AC082651.1
AC084346.2
AC084824.4
AC092171.4
AC092803.2

AC084346.2
AD097808.3
AC084824.4
ADFR3564.8
A1982983.4

AC098789.3
AC022509.2
AC783546.3
AC055720.2

AC018653.3
AS989473.9
AC022509.1
AE378467.1

M_B.csv: AC084346.2, AC084824.4
M_C.csv: AC022509.2, AC055720.2
M_D.csv: AC018653.3, AC022509.1

setwd("/data/")
library(tidyverse)
library(magrittr)

genes <- Sys.glob(file.path("M_*.csv"))
genes.read <- lapply(genes,function(x) read.delim(x, header = FALSE))
genes.read <- lapply(genes.read, function(x) set_colnames(x, "Genes"))
ref2 <- list.files(pattern = "UP")
ref2
ref.read <- read.delim(ref2[[1]])
intersect <- lapply(seq_along(genes.read), function(x) 
  intersect(genes.read[[x]], ref.read))
for(i in 1:length(genes.read)) { 
  cat(genes[[i]],":",intersect[[i]]$Genes, "\n")
}

M_B.csv

有如下内容：

data
  |___ UPA.csv
  |___ M_B.csv
  |___ M_C.csv
  |___ M_D.csv
  |___ M_E.csv

Genes
AC018653.3
AC022509.1
AC022509.2
AC055720.2
AC082651.1
AC084346.2
AC084824.4
AC092171.4
AC092803.2

AC084346.2
AD097808.3
AC084824.4
ADFR3564.8
A1982983.4

AC098789.3
AC022509.2
AC783546.3
AC055720.2

AC018653.3
AS989473.9
AC022509.1
AE378467.1

M_B.csv: AC084346.2, AC084824.4
M_C.csv: AC022509.2, AC055720.2
M_D.csv: AC018653.3, AC022509.1

setwd("/data/")
library(tidyverse)
library(magrittr)

genes <- Sys.glob(file.path("M_*.csv"))
genes.read <- lapply(genes,function(x) read.delim(x, header = FALSE))
genes.read <- lapply(genes.read, function(x) set_colnames(x, "Genes"))
ref2 <- list.files(pattern = "UP")
ref2
ref.read <- read.delim(ref2[[1]])
intersect <- lapply(seq_along(genes.read), function(x) 
  intersect(genes.read[[x]], ref.read))
for(i in 1:length(genes.read)) { 
  cat(genes[[i]],":",intersect[[i]]$Genes, "\n")
}

M_C.csv

有如下内容：

data
  |___ UPA.csv
  |___ M_B.csv
  |___ M_C.csv
  |___ M_D.csv
  |___ M_E.csv

Genes
AC018653.3
AC022509.1
AC022509.2
AC055720.2
AC082651.1
AC084346.2
AC084824.4
AC092171.4
AC092803.2

AC084346.2
AD097808.3
AC084824.4
ADFR3564.8
A1982983.4

AC098789.3
AC022509.2
AC783546.3
AC055720.2

AC018653.3
AS989473.9
AC022509.1
AE378467.1

M_B.csv: AC084346.2, AC084824.4
M_C.csv: AC022509.2, AC055720.2
M_D.csv: AC018653.3, AC022509.1

setwd("/data/")
library(tidyverse)
library(magrittr)

genes <- Sys.glob(file.path("M_*.csv"))
genes.read <- lapply(genes,function(x) read.delim(x, header = FALSE))
genes.read <- lapply(genes.read, function(x) set_colnames(x, "Genes"))
ref2 <- list.files(pattern = "UP")
ref2
ref.read <- read.delim(ref2[[1]])
intersect <- lapply(seq_along(genes.read), function(x) 
  intersect(genes.read[[x]], ref.read))
for(i in 1:length(genes.read)) { 
  cat(genes[[i]],":",intersect[[i]]$Genes, "\n")
}

M_D.csv

有如下内容：

data
  |___ UPA.csv
  |___ M_B.csv
  |___ M_C.csv
  |___ M_D.csv
  |___ M_E.csv

Genes
AC018653.3
AC022509.1
AC022509.2
AC055720.2
AC082651.1
AC084346.2
AC084824.4
AC092171.4
AC092803.2

AC084346.2
AD097808.3
AC084824.4
ADFR3564.8
A1982983.4

AC098789.3
AC022509.2
AC783546.3
AC055720.2

AC018653.3
AS989473.9
AC022509.1
AE378467.1

M_B.csv: AC084346.2, AC084824.4
M_C.csv: AC022509.2, AC055720.2
M_D.csv: AC018653.3, AC022509.1

setwd("/data/")
library(tidyverse)
library(magrittr)

genes <- Sys.glob(file.path("M_*.csv"))
genes.read <- lapply(genes,function(x) read.delim(x, header = FALSE))
genes.read <- lapply(genes.read, function(x) set_colnames(x, "Genes"))
ref2 <- list.files(pattern = "UP")
ref2
ref.read <- read.delim(ref2[[1]])
intersect <- lapply(seq_along(genes.read), function(x) 
  intersect(genes.read[[x]], ref.read))
for(i in 1:length(genes.read)) { 
  cat(genes[[i]],":",intersect[[i]]$Genes, "\n")
}

我想检查

UPA.csv

中的哪些

基因也在其他文件中找到。并希望获得文件名
我希望输出如下所示：
data
  |___ UPA.csv
  |___ M_B.csv
  |___ M_C.csv
  |___ M_D.csv
  |___ M_E.csv

Genes
AC018653.3
AC022509.1
AC022509.2
AC055720.2
AC082651.1
AC084346.2
AC084824.4
AC092171.4
AC092803.2

AC084346.2
AD097808.3
AC084824.4
ADFR3564.8
A1982983.4

AC098789.3
AC022509.2
AC783546.3
AC055720.2

AC018653.3
AS989473.9
AC022509.1
AE378467.1

M_B.csv: AC084346.2, AC084824.4
M_C.csv: AC022509.2, AC055720.2
M_D.csv: AC018653.3, AC022509.1

setwd("/data/")
library(tidyverse)
library(magrittr)

genes <- Sys.glob(file.path("M_*.csv"))
genes.read <- lapply(genes,function(x) read.delim(x, header = FALSE))
genes.read <- lapply(genes.read, function(x) set_colnames(x, "Genes"))
ref2 <- list.files(pattern = "UP")
ref2
ref.read <- read.delim(ref2[[1]])
intersect <- lapply(seq_along(genes.read), function(x) 
  intersect(genes.read[[x]], ref.read))
for(i in 1:length(genes.read)) { 
  cat(genes[[i]],":",intersect[[i]]$Genes, "\n")
}

为此，我尝试如下：
data
  |___ UPA.csv
  |___ M_B.csv
  |___ M_C.csv
  |___ M_D.csv
  |___ M_E.csv

Genes
AC018653.3
AC022509.1
AC022509.2
AC055720.2
AC082651.1
AC084346.2
AC084824.4
AC092171.4
AC092803.2

AC084346.2
AD097808.3
AC084824.4
ADFR3564.8
A1982983.4

AC098789.3
AC022509.2
AC783546.3
AC055720.2

AC018653.3
AS989473.9
AC022509.1
AE378467.1

M_B.csv: AC084346.2, AC084824.4
M_C.csv: AC022509.2, AC055720.2
M_D.csv: AC018653.3, AC022509.1

setwd("/data/")
library(tidyverse)
library(magrittr)

genes <- Sys.glob(file.path("M_*.csv"))
genes.read <- lapply(genes,function(x) read.delim(x, header = FALSE))
genes.read <- lapply(genes.read, function(x) set_colnames(x, "Genes"))
ref2 <- list.files(pattern = "UP")
ref2
ref.read <- read.delim(ref2[[1]])
intersect <- lapply(seq_along(genes.read), function(x) 
  intersect(genes.read[[x]], ref.read))
for(i in 1:length(genes.read)) { 
  cat(genes[[i]],":",intersect[[i]]$Genes, "\n")
}

请尝试以下操作：
UPA <- read.csv('UPA.csv')
filenames <- list.files(pattern = 'M_.*\\.csv$')

do.call(rbind, lapply(filenames, function(x) {
  data <- read.delim(x, header = FALSE)
  names(data) <- 'Genes'
  cbind(file = x, subset(data, Genes %in% UPA$Genes))
})) -> result

这将为您提供如下输出：
result

#       Genes    file 
#1 AC084346.2 M_B.csv
#2 AC084824.4 M_B.csv
#3 AC022509.2 M_C.csv
#4 AC055720.2 M_C.csv
#...

非常感谢。对于tidyverse
，什么是list\u dat
？对不起，应该是文件名。我已经更新了答案。